Research Repository

General Video Game AI: Learning from screen capture

Kunanusont, K and Lucas, SM and Perez Liebana, D (2017) General Video Game AI: Learning from screen capture. In: IEEE Congress on Evolutionary Computation (CEC), 2017, 2017-06-05 - 2017-06-08, San Sebastian, Spain.

[img]
Preview
Text
1704.06945v1.pdf - Accepted Version

Download (1MB) | Preview

Abstract

General Video Game Artificial Intelligence is a general game playing framework for Artificial General Intelligence research in the video-games domain. In this paper, we propose for the first time a screen capture learning agent for General Video Game AI framework. A Deep Q-Network algorithm was applied and improved to develop an agent capable of learning to play different games in the framework. After testing this algorithm using various games of different categories and difficulty levels, the results suggest that our proposed screen capture learning agent has the potential to learn many different games using only a single learning algorithm.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: 2017 IEEE Congress on Evolutionary Computation, CEC 2017 - Proceedings
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 08 Sep 2017 12:59
Last Modified: 28 Nov 2017 16:15
URI: http://repository.essex.ac.uk/id/eprint/20342

Actions (login required)

View Item View Item